verify_embedding_policy
Check embedding vectors.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| vector | No |
1cnf-verifier
TDQS
C2/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden of explaining behavior. 'Check embedding vectors' gives a minimal suggestion of a read-only validation, but does not disclose return format, side effects, error behavior, or how the policy is enforced.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short, but this is under-specification rather than effective conciseness. A single vague sentence does not serve the tool's semantic needs and provides no structured information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, no annotations, no parameter documentation, and no usage guidance. The description is the only context but is far too thin to let an agent understand inputs, behavior, or return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema defines a single 'vector' array with no description and 0% schema coverage, so the description must compensate. It adds only a vague hint that the array represents embedding vectors; it does not explain expected dimensions, value ranges, or how the vector is evaluated.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description says 'Check embedding vectors,' which provides a verb and a resource, so it is not a pure tautology. However, it is vague: it does not explain what policy is being verified, what the check consists of, or what makes the result valid or invalid. It also does not distinguish it from sibling verify/check tools beyond the mention of vectors.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage context is provided. There is no mention of when this tool should be used instead of siblings like verify_risk_policy or check_threat_blacklist, and no prerequisites, warnings, or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Try in Browser
Glama MCP Gateway
Add one secure layer between your agents and this server.
TDQS
C2.7/5.0
Disambiguation4/5
Each tool targets a distinct verification concern—hashes, state intervals, agent policies, plan trajectories, embeddings, trade bounds, memory assertions, and risk vectors. The close pairing of verify_1cnf_invariants and verify_liquidity_invariant is mitigated by their clear descriptions, though both being 'invariant' checks creates slight potential for confusion.
Naming Consistency4/5
The overwhelming majority follow a consistent verify_<domain> pattern, making the set predictable. The single exception is check_threat_blacklist, which swaps 'verify' for 'check', creating a minor deviation without breaking overall readability.
Tool Count5/5
Eight tools is well within the ideal range and suits a verification-focused server. Each tool covers a distinct verification category, and none feel redundant or superfluous.
Completeness4/5
The tool surface covers a broad set of verification domains—security, invariants, planning, embeddings, liquidity, memory, and risk. It lacks an aggregate 'run all verifications' or status tool, but the individual coverage is strong enough that agents can perform the intended verification workflows.